Wyniki wyszukiwania - BazTech

1

Reasoning algorithm for a creative decision support system integrating inference and machine learning

Wilk-Kolodziejczyk D.

Computer Science

|

2017

|

Vol. 18 (3)

317--338

EN

In this paper a reasoning algorithm for a creative decision support system is proposed. It allows to integrate inference and machine learning algorithms. Execution of learning algorithm is automatic because it is formalized as aplying a complex inference rule, which generates intrinsically new knowledge using the facts stored already in the knowledge base as training data. This new knowledge may be used in the same inference chain to derive a decision. Such a solution makes the reasoning process more creative and allows to continue resoning in cases when the knowledge base does not have appropriate knowledge explicit encoded. In the paper appropriate knowledge representation and infeence model are proposed. Experimental verification is performed on a decision support system in a casting domain.

2

The Heuristic Model Based on LPR in the Context of Material Conversion

Wilk-Kołodziejczyk D., Kluska-Nawarecka S., Nawarecki E., Śnieżyński B., Jaśkowiec K., Legień G.

Archives of Metallurgy and Materials

|

2017

|

Vol. 62, iss. 3

1603--1607

EN

High complexity of the physical and chemical processes occurring in liquid metal is the reason why it is so difficult, impossible even sometimes, to make analytical models of these phenomena. In this situation, the use of heuristic models based on the experimental data and experience of technicians is fully justified since, in an approximate manner at least, they allow predicting the mechanical properties of the metal manufactured under given process conditions. The study presents a methodology applicable in the design of a heuristic model based on the formalism of the logic of plausible reasoning (LPR). The problem under consideration consists in finding a technological variant of the process that will give the desired product parameters while minimizing the cost of production. The conducted tests have shown the effectiveness of the proposed approach.

3

The use of LPR (logic of plausible reasoning) to obtain information on innovative casting technologies

Kluska-Nawarecka S., Śnieżyński B., Parada W., Lustofin M., Wilk-Kołodziejczyk D.

Archives of Civil and Mechanical Engineering

|

2014

|

Vol. 14, no. 1

25--31

EN

The paper presents a methodology for the application of a formalism of the logic of plausible reasoning (LPR) to create knowledge about a specific problem area. In this case, the methodology has been related to the task of obtaining information about the innovative casting technologies. In the search for documents, formulas created in terms of LPR have a much greater expressive power than the commonly used keywords. The discussion was illustrated with the results obtained using a pilot version of the original information tool.

4

Diagnosis of casting defects using uncertain and incomplete knowledge

Górny Z., Kluska-Nawarecka S., Wilk-Kołodziejczyk D., Regulski K.

Archives of Metallurgy and Materials

|

2010

|

Vol. 55, iss. 3

827-836

EN

Diagnosis of the causes of casting defects is a difficult task. Many of the premises for defect diagnosis are intuitive, and therefore creation of systems for defect diagnosis must be supported by tools that can collect and use incomplete and uncertain knowledge. The aim of this article was to create a perspective in the formation of systems operating knowledge of this class. The problem that remains open is creating a knowledge base, adapted to particular casting technologies, and improvement of an interface oriented at the specific user needs. The article presents two methods selected for the construction of models of reasoning, i.e. the method based on fuzzy logic and the method based on the logic of plausible reasoning. While solutions based on the use of fuzzy logic have already found some approval in a number of practical applications and can be used as a point of reference, the logic of plausible reasoning still remains in this area a formalism quite innovative. In this study, apart from formal discussions, examples of fragments of the knowledge about the defects in castings and related algorithmic solutions and tools were presented.

PL

Diagnostyka przyczyn powstawania wad odlewniczych jest trudnym zadaniem. Wiele przesłanek dotyczacych diagnostyki wad jest intuicyjnych, dlatego tworzenie systemów wspomagających diagnostykę wad musi byc wsparte narzędziami, które potrafią gromadzić i następnie wykorzystywać wiedzę niepełna i niepewna. Zamierzaniem artykułu było stworzenie pewnej perspektywy odnośnie stworzenia systemów operujących tej klasy wiedzą. Problemem pozostaje tu stworzenie bazy wiedzy, dostosowanej do konkretnych technologii odlewniczych, a także doskonalenie interfejsu zorientowanego na specyficzne potrzeby użytkownika. Artykuł prezentuje dwie wybrane metody budowy modeli wnioskowania: w oparciu o logike rozmyta oraz logike wiarygodnego rozumowania. O ile rozwiązania oparte na zastosowaniu logiki rozmytej uzyskały juz pewne potwierdzenie w szeregu zastosowaniach praktycznych i może stanowić pewien punkt odniesienia, o tyle logika wiarygodnego rozumowania jest w tym zakresie formalizmem całkiem innowacyjnym. W pracy obok rozważań formalnych przedstawiono przykłady fragmentów wiedzy o wadach odlewów oraz odnośne rozwiązania algorytmiczne i narzędziowe.

5

The logistic of plausible reasoning in the diagnosis of castings defects

Kluska-Nawarecka S., Górny Z., Wilk-Kołodziejczyk D., Smolarek-Grzyb A.

Archives of Metallurgy and Materials

|

2007

|

Vol. 52, iss. 3

375-380

EN

Quick diagnosis of the cause of crack formation enables preventing the formation of other cracks in the next casting process and enables also, as far as it is possible, a repair of the existing defect. In this task expert systems are a very useful tool. The efficiency of an expert system diagnosis depends on the data entered previously and on the way in which the knowledge is represented. In the article there has been presented the Logic of Plausible Reasoning with the rules of its usage on the example of “crack” fault. Drawing attention to advantages of such an approach in relation to solutions used in existing expert systems.

PL

Szybka diagnostyka przyczyny powstania wady pozwala na nie dopuszczenie do powstania nowych w kolejnym procesie odlewania, oraz jeżeli to możliwe naprawienie powstałej. W procesie takim bardzo pomocne są systemy ekspertowe. Skuteczność ich diagnozy uzależniona jest od informacji wprowadzonych do nich oraz od sposobu reprezentacji tej wiedzy. W pracy podano krótką charakterystykę LPR ilustrując zasady jej wykorzystanie na przykładzie wady „pęknięcie”. Zwracając uwagę na zalety proponowanego podejścia, w stosunku do rozwiązań stosowanych w istniejących systemach ekspertowych.

6

Diagnostics of crack formation in castings using the logic of plausible reasoning

Kluska-Nawarecka S., Górny Z., Wilk-Kołodziejczyk D., Smolarek-Grzyb A.

Archives of Materials Science and Engineering

|

2007

|

Vol. 28, nr 8

479-482

EN

Purpose: Cold cracks are the defect often encountered in castings. Quick diagnosis of the cause of crack formation enables preventing the formation of other cracks in the next casting process and enables also, as far as it is possible, a repair of the existing defect. In this task expert systems are a very useful tool. Design/methodology/approach: Standard of Casting Defects elaborated in Poland, Atlas of Casting Defects elaborated in France, and a Review of Casting Defects elaborated in the Czech Republic. These sources are the knowledge compendium of casting defects. Basing on such information, serving as a defect description, the cause of the defect formation and the way of preventing it have been created as formalisms which enable an inference to be carried out, the aim of which is to establish the cause of the defect. Findings: The use of LPR (the Logic of Plausible Reasoning) in the representation of knowledge about casting defects introduces a new quality, allowing to take into consideration the specific characteristics of this knowledge such as: uncertainty, definitions hierarchy, the possibility of introducing the diagnostics ranking. In consequence, the diagnostic process becomes more flexible and may be better adjusted to the real technological process conditions. Practical implications: The efficiency of an expert system diagnosis depends on the data entered previously and on the way in which the knowledge is represented. Originality/value: In this article various representations of the knowledge have been presented by means of the logic of plausible reasoning.